Skip to content

Author

Jinha Kim

We have 2 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Delayed Supervision for Test-Time Language Models

Delayed semantic supervision as a practical outer training objective for usable test-time memory is supported, while leaving open how much of the benefit derives specifically from delay rather than general question-answering and answer-termination supervision.

Jinha Kim, Taksh Kothari · 0 citations
Open access Aug 2026

ProtJEPA: A Multimodal Joint-Embedding Predictive Architecture for Protein Biological World Modeling with Multi-Teacher Modality-Attentive Fusion

Under realistic dark-protein deployment conditions where relational modalities are unavailable, ProtJEPA significantly outperforms naive concatenation of remaining modalities and cross-domain evaluations on drug–target interaction and disorder prediction confirm transfer beyond training modalities.

Vaibhava Lakshmi Ravideshik, Jinha Kim, M. Kellis · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.